{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 966,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 5.154639175257731e-09,
      "logits/generated": -3.219531536102295,
      "logits/real": -2.9386723041534424,
      "logps/generated": -108.60189056396484,
      "logps/real": -144.99282836914062,
      "loss": 0.6931,
      "rewards/accuracies": 0.0,
      "rewards/generated": 0.0,
      "rewards/margins": 0.0,
      "rewards/real": 0.0,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.154639175257731e-08,
      "logits/generated": -3.065950870513916,
      "logits/real": -2.903123140335083,
      "logps/generated": -105.72628021240234,
      "logps/real": -133.1763153076172,
      "loss": 0.6331,
      "rewards/accuracies": 0.7361111044883728,
      "rewards/generated": -0.09165798872709274,
      "rewards/margins": 0.1280461698770523,
      "rewards/real": 0.03638818860054016,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.0309278350515462e-07,
      "logits/generated": -3.0428578853607178,
      "logits/real": -2.8581371307373047,
      "logps/generated": -106.27662658691406,
      "logps/real": -129.45240783691406,
      "loss": 0.2429,
      "rewards/accuracies": 1.0,
      "rewards/generated": -1.2017046213150024,
      "rewards/margins": 1.5348618030548096,
      "rewards/real": 0.3331572413444519,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.5463917525773197e-07,
      "logits/generated": -2.94812273979187,
      "logits/real": -2.7271862030029297,
      "logps/generated": -125.34303283691406,
      "logps/real": -113.06243896484375,
      "loss": 0.1009,
      "rewards/accuracies": 1.0,
      "rewards/generated": -2.5681145191192627,
      "rewards/margins": 3.2362685203552246,
      "rewards/real": 0.6681544184684753,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.0618556701030925e-07,
      "logits/generated": -2.9616527557373047,
      "logits/real": -2.676217555999756,
      "logps/generated": -130.88194274902344,
      "logps/real": -109.51456451416016,
      "loss": 0.0583,
      "rewards/accuracies": 1.0,
      "rewards/generated": -3.2980754375457764,
      "rewards/margins": 4.2449049949646,
      "rewards/real": 0.9468294978141785,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.5773195876288655e-07,
      "logits/generated": -2.947620391845703,
      "logits/real": -2.7104084491729736,
      "logps/generated": -128.3996124267578,
      "logps/real": -113.8232421875,
      "loss": 0.0534,
      "rewards/accuracies": 1.0,
      "rewards/generated": -3.5237224102020264,
      "rewards/margins": 4.472705841064453,
      "rewards/real": 0.9489830732345581,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.0927835051546394e-07,
      "logits/generated": -2.9422521591186523,
      "logits/real": -2.6731066703796387,
      "logps/generated": -146.13998413085938,
      "logps/real": -115.45304107666016,
      "loss": 0.0263,
      "rewards/accuracies": 1.0,
      "rewards/generated": -4.71472692489624,
      "rewards/margins": 5.738630294799805,
      "rewards/real": 1.0239028930664062,
      "step": 60
    },
    {
      "epoch": 0.07,
      "learning_rate": 3.608247422680412e-07,
      "logits/generated": -2.91066312789917,
      "logits/real": -2.6730122566223145,
      "logps/generated": -145.42698669433594,
      "logps/real": -119.39422607421875,
      "loss": 0.0256,
      "rewards/accuracies": 1.0,
      "rewards/generated": -5.199321746826172,
      "rewards/margins": 6.081934928894043,
      "rewards/real": 0.8826133608818054,
      "step": 70
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.123711340206185e-07,
      "logits/generated": -2.878272771835327,
      "logits/real": -2.6425604820251465,
      "logps/generated": -164.4766845703125,
      "logps/real": -114.11893463134766,
      "loss": 0.0152,
      "rewards/accuracies": 1.0,
      "rewards/generated": -6.381728649139404,
      "rewards/margins": 7.309477806091309,
      "rewards/real": 0.9277499914169312,
      "step": 80
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.639175257731959e-07,
      "logits/generated": -2.867196798324585,
      "logits/real": -2.632091760635376,
      "logps/generated": -167.42098999023438,
      "logps/real": -111.54139709472656,
      "loss": 0.0143,
      "rewards/accuracies": 1.0,
      "rewards/generated": -7.244837284088135,
      "rewards/margins": 8.004537582397461,
      "rewards/real": 0.7597017884254456,
      "step": 90
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.982738780207135e-07,
      "logits/generated": -2.7975480556488037,
      "logits/real": -2.579317569732666,
      "logps/generated": -181.7258758544922,
      "logps/real": -118.5848617553711,
      "loss": 0.0085,
      "rewards/accuracies": 1.0,
      "rewards/generated": -8.4071683883667,
      "rewards/margins": 8.880010604858398,
      "rewards/real": 0.47284331917762756,
      "step": 100
    },
    {
      "epoch": 0.1,
      "eval_logits/generated": -2.791118621826172,
      "eval_logits/real": -2.5501742362976074,
      "eval_logps/generated": -186.5558624267578,
      "eval_logps/real": -119.72185516357422,
      "eval_loss": 0.012979106977581978,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -9.329732894897461,
      "eval_rewards/margins": 9.852580070495605,
      "eval_rewards/real": 0.5228471755981445,
      "eval_runtime": 209.1023,
      "eval_samples_per_second": 14.629,
      "eval_steps_per_second": 0.459,
      "step": 100
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.925201380897583e-07,
      "logits/generated": -2.785588026046753,
      "logits/real": -2.488529920578003,
      "logps/generated": -189.90138244628906,
      "logps/real": -117.48527526855469,
      "loss": 0.0123,
      "rewards/accuracies": 1.0,
      "rewards/generated": -9.674561500549316,
      "rewards/margins": 10.426921844482422,
      "rewards/real": 0.7523608803749084,
      "step": 110
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.867663981588032e-07,
      "logits/generated": -2.7283473014831543,
      "logits/real": -2.566411256790161,
      "logps/generated": -194.92166137695312,
      "logps/real": -128.1994171142578,
      "loss": 0.012,
      "rewards/accuracies": 1.0,
      "rewards/generated": -10.19434928894043,
      "rewards/margins": 10.776617050170898,
      "rewards/real": 0.5822684168815613,
      "step": 120
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.81012658227848e-07,
      "logits/generated": -2.7403314113616943,
      "logits/real": -2.515610456466675,
      "logps/generated": -208.9757537841797,
      "logps/real": -117.58453369140625,
      "loss": 0.0087,
      "rewards/accuracies": 1.0,
      "rewards/generated": -10.878945350646973,
      "rewards/margins": 10.95063591003418,
      "rewards/real": 0.07169149070978165,
      "step": 130
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.7525891829689296e-07,
      "logits/generated": -2.7327401638031006,
      "logits/real": -2.4573469161987305,
      "logps/generated": -209.5993194580078,
      "logps/real": -133.99539184570312,
      "loss": 0.0102,
      "rewards/accuracies": 1.0,
      "rewards/generated": -11.155704498291016,
      "rewards/margins": 10.907458305358887,
      "rewards/real": -0.24824699759483337,
      "step": 140
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.695051783659378e-07,
      "logits/generated": -2.6974403858184814,
      "logits/real": -2.355384111404419,
      "logps/generated": -199.15945434570312,
      "logps/real": -132.37490844726562,
      "loss": 0.0041,
      "rewards/accuracies": 1.0,
      "rewards/generated": -10.489466667175293,
      "rewards/margins": 10.455119132995605,
      "rewards/real": -0.03434727340936661,
      "step": 150
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.637514384349827e-07,
      "logits/generated": -2.824667453765869,
      "logits/real": -2.5955474376678467,
      "logps/generated": -187.07211303710938,
      "logps/real": -129.47560119628906,
      "loss": 0.0078,
      "rewards/accuracies": 1.0,
      "rewards/generated": -9.341938972473145,
      "rewards/margins": 9.66246223449707,
      "rewards/real": 0.3205236494541168,
      "step": 160
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.579976985040276e-07,
      "logits/generated": -2.8009626865386963,
      "logits/real": -2.4973556995391846,
      "logps/generated": -213.91030883789062,
      "logps/real": -129.75320434570312,
      "loss": 0.0037,
      "rewards/accuracies": 1.0,
      "rewards/generated": -11.317999839782715,
      "rewards/margins": 11.145898818969727,
      "rewards/real": -0.17210128903388977,
      "step": 170
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.5224395857307246e-07,
      "logits/generated": -2.7977960109710693,
      "logits/real": -2.578437566757202,
      "logps/generated": -216.72470092773438,
      "logps/real": -124.4120864868164,
      "loss": 0.0034,
      "rewards/accuracies": 1.0,
      "rewards/generated": -11.642924308776855,
      "rewards/margins": 11.94387149810791,
      "rewards/real": 0.30094677209854126,
      "step": 180
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.4649021864211733e-07,
      "logits/generated": -2.6713316440582275,
      "logits/real": -2.3220620155334473,
      "logps/generated": -230.6079559326172,
      "logps/real": -126.48348236083984,
      "loss": 0.009,
      "rewards/accuracies": 1.0,
      "rewards/generated": -13.57984733581543,
      "rewards/margins": 13.31432819366455,
      "rewards/real": -0.26552003622055054,
      "step": 190
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.4073647871116224e-07,
      "logits/generated": -2.688673496246338,
      "logits/real": -2.3426332473754883,
      "logps/generated": -230.0777130126953,
      "logps/real": -129.56216430664062,
      "loss": 0.0041,
      "rewards/accuracies": 1.0,
      "rewards/generated": -13.36060619354248,
      "rewards/margins": 13.484850883483887,
      "rewards/real": 0.12424616515636444,
      "step": 200
    },
    {
      "epoch": 0.21,
      "eval_logits/generated": -2.6228020191192627,
      "eval_logits/real": -2.2903988361358643,
      "eval_logps/generated": -241.2277374267578,
      "eval_logps/real": -126.65628814697266,
      "eval_loss": 0.006963553372770548,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -14.796919822692871,
      "eval_rewards/margins": 14.626323699951172,
      "eval_rewards/real": -0.17059551179409027,
      "eval_runtime": 205.264,
      "eval_samples_per_second": 14.903,
      "eval_steps_per_second": 0.468,
      "step": 200
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.3498273878020716e-07,
      "logits/generated": -2.6520376205444336,
      "logits/real": -2.311628818511963,
      "logps/generated": -243.22134399414062,
      "logps/real": -132.87661743164062,
      "loss": 0.0049,
      "rewards/accuracies": 1.0,
      "rewards/generated": -14.594164848327637,
      "rewards/margins": 14.171404838562012,
      "rewards/real": -0.4227598309516907,
      "step": 210
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.29228998849252e-07,
      "logits/generated": -2.6436614990234375,
      "logits/real": -2.2886173725128174,
      "logps/generated": -259.21002197265625,
      "logps/real": -129.3766632080078,
      "loss": 0.005,
      "rewards/accuracies": 1.0,
      "rewards/generated": -16.33755874633789,
      "rewards/margins": 15.9202880859375,
      "rewards/real": -0.41726917028427124,
      "step": 220
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.234752589182969e-07,
      "logits/generated": -2.62636661529541,
      "logits/real": -2.125588893890381,
      "logps/generated": -264.7667236328125,
      "logps/real": -135.39988708496094,
      "loss": 0.0028,
      "rewards/accuracies": 1.0,
      "rewards/generated": -16.985706329345703,
      "rewards/margins": 15.743583679199219,
      "rewards/real": -1.242120623588562,
      "step": 230
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.1772151898734174e-07,
      "logits/generated": -2.6304118633270264,
      "logits/real": -1.9994169473648071,
      "logps/generated": -272.40142822265625,
      "logps/real": -131.99339294433594,
      "loss": 0.002,
      "rewards/accuracies": 1.0,
      "rewards/generated": -17.400745391845703,
      "rewards/margins": 16.010761260986328,
      "rewards/real": -1.3899824619293213,
      "step": 240
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.1196777905638666e-07,
      "logits/generated": -2.639122486114502,
      "logits/real": -2.190335988998413,
      "logps/generated": -249.3017578125,
      "logps/real": -141.9188995361328,
      "loss": 0.0018,
      "rewards/accuracies": 1.0,
      "rewards/generated": -15.32465934753418,
      "rewards/margins": 14.79564380645752,
      "rewards/real": -0.5290150046348572,
      "step": 250
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.062140391254315e-07,
      "logits/generated": -2.637878894805908,
      "logits/real": -2.19781756401062,
      "logps/generated": -257.8635559082031,
      "logps/real": -132.95468139648438,
      "loss": 0.0019,
      "rewards/accuracies": 1.0,
      "rewards/generated": -16.294628143310547,
      "rewards/margins": 16.130474090576172,
      "rewards/real": -0.1641537845134735,
      "step": 260
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.004602991944764e-07,
      "logits/generated": -2.5847439765930176,
      "logits/real": -2.062397003173828,
      "logps/generated": -274.86383056640625,
      "logps/real": -158.84170532226562,
      "loss": 0.0032,
      "rewards/accuracies": 1.0,
      "rewards/generated": -17.955219268798828,
      "rewards/margins": 16.333662033081055,
      "rewards/real": -1.6215585470199585,
      "step": 270
    },
    {
      "epoch": 0.29,
      "learning_rate": 3.9470655926352124e-07,
      "logits/generated": -2.562634229660034,
      "logits/real": -1.933498740196228,
      "logps/generated": -288.2635498046875,
      "logps/real": -133.76516723632812,
      "loss": 0.0011,
      "rewards/accuracies": 1.0,
      "rewards/generated": -19.188732147216797,
      "rewards/margins": 17.58678436279297,
      "rewards/real": -1.6019468307495117,
      "step": 280
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.889528193325661e-07,
      "logits/generated": -2.5373287200927734,
      "logits/real": -1.9189929962158203,
      "logps/generated": -290.69000244140625,
      "logps/real": -129.52732849121094,
      "loss": 0.004,
      "rewards/accuracies": 1.0,
      "rewards/generated": -19.61493492126465,
      "rewards/margins": 18.025314331054688,
      "rewards/real": -1.5896228551864624,
      "step": 290
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.83199079401611e-07,
      "logits/generated": -2.5227181911468506,
      "logits/real": -1.8413000106811523,
      "logps/generated": -328.73858642578125,
      "logps/real": -149.974365234375,
      "loss": 0.0007,
      "rewards/accuracies": 1.0,
      "rewards/generated": -22.51827621459961,
      "rewards/margins": 20.30518913269043,
      "rewards/real": -2.2130885124206543,
      "step": 300
    },
    {
      "epoch": 0.31,
      "eval_logits/generated": -2.482497453689575,
      "eval_logits/real": -1.9073033332824707,
      "eval_logps/generated": -317.1597595214844,
      "eval_logps/real": -152.65652465820312,
      "eval_loss": 0.007317742798477411,
      "eval_rewards/accuracies": 0.9973958134651184,
      "eval_rewards/generated": -22.390119552612305,
      "eval_rewards/margins": 19.61949920654297,
      "eval_rewards/real": -2.770620346069336,
      "eval_runtime": 205.5131,
      "eval_samples_per_second": 14.885,
      "eval_steps_per_second": 0.467,
      "step": 300
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.7744533947065594e-07,
      "logits/generated": -2.465297222137451,
      "logits/real": -1.8258562088012695,
      "logps/generated": -324.6069641113281,
      "logps/real": -159.44512939453125,
      "loss": 0.0004,
      "rewards/accuracies": 1.0,
      "rewards/generated": -22.71963882446289,
      "rewards/margins": 19.57671356201172,
      "rewards/real": -3.142927408218384,
      "step": 310
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.716915995397008e-07,
      "logits/generated": -2.6246092319488525,
      "logits/real": -2.2683050632476807,
      "logps/generated": -243.05075073242188,
      "logps/real": -146.40414428710938,
      "loss": 0.0053,
      "rewards/accuracies": 1.0,
      "rewards/generated": -14.549066543579102,
      "rewards/margins": 13.9031343460083,
      "rewards/real": -0.6459320783615112,
      "step": 320
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.6593785960874566e-07,
      "logits/generated": -2.7059178352355957,
      "logits/real": -2.3165206909179688,
      "logps/generated": -241.59780883789062,
      "logps/real": -138.5386199951172,
      "loss": 0.0052,
      "rewards/accuracies": 1.0,
      "rewards/generated": -13.953645706176758,
      "rewards/margins": 13.269960403442383,
      "rewards/real": -0.6836851835250854,
      "step": 330
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.601841196777906e-07,
      "logits/generated": -2.7283644676208496,
      "logits/real": -2.3756351470947266,
      "logps/generated": -219.77841186523438,
      "logps/real": -130.38873291015625,
      "loss": 0.003,
      "rewards/accuracies": 1.0,
      "rewards/generated": -12.349191665649414,
      "rewards/margins": 12.542909622192383,
      "rewards/real": 0.19371815025806427,
      "step": 340
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.5443037974683544e-07,
      "logits/generated": -2.6958298683166504,
      "logits/real": -2.277108907699585,
      "logps/generated": -226.6746368408203,
      "logps/real": -114.52205657958984,
      "loss": 0.006,
      "rewards/accuracies": 1.0,
      "rewards/generated": -12.923785209655762,
      "rewards/margins": 13.137397766113281,
      "rewards/real": 0.2136126309633255,
      "step": 350
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.486766398158803e-07,
      "logits/generated": -2.7013585567474365,
      "logits/real": -2.2646822929382324,
      "logps/generated": -238.26022338867188,
      "logps/real": -115.47855377197266,
      "loss": 0.0015,
      "rewards/accuracies": 1.0,
      "rewards/generated": -14.308649063110352,
      "rewards/margins": 14.47448444366455,
      "rewards/real": 0.16583377122879028,
      "step": 360
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.4292289988492516e-07,
      "logits/generated": -2.694920778274536,
      "logits/real": -2.3415982723236084,
      "logps/generated": -230.7061309814453,
      "logps/real": -128.92630004882812,
      "loss": 0.0026,
      "rewards/accuracies": 1.0,
      "rewards/generated": -14.068750381469727,
      "rewards/margins": 14.175163269042969,
      "rewards/real": 0.1064140647649765,
      "step": 370
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.371691599539701e-07,
      "logits/generated": -2.686997890472412,
      "logits/real": -2.3440613746643066,
      "logps/generated": -244.41323852539062,
      "logps/real": -137.19679260253906,
      "loss": 0.0019,
      "rewards/accuracies": 1.0,
      "rewards/generated": -15.056386947631836,
      "rewards/margins": 14.345705032348633,
      "rewards/real": -0.7106844186782837,
      "step": 380
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.3141542002301494e-07,
      "logits/generated": -2.6631417274475098,
      "logits/real": -2.199228286743164,
      "logps/generated": -274.129638671875,
      "logps/real": -135.17514038085938,
      "loss": 0.002,
      "rewards/accuracies": 1.0,
      "rewards/generated": -17.713571548461914,
      "rewards/margins": 16.622684478759766,
      "rewards/real": -1.0908849239349365,
      "step": 390
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.256616800920598e-07,
      "logits/generated": -2.625967025756836,
      "logits/real": -2.197558879852295,
      "logps/generated": -290.901611328125,
      "logps/real": -150.78567504882812,
      "loss": 0.0049,
      "rewards/accuracies": 1.0,
      "rewards/generated": -19.44015884399414,
      "rewards/margins": 17.009281158447266,
      "rewards/real": -2.4308791160583496,
      "step": 400
    },
    {
      "epoch": 0.41,
      "eval_logits/generated": -2.600975751876831,
      "eval_logits/real": -2.2354793548583984,
      "eval_logps/generated": -288.20526123046875,
      "eval_logps/real": -154.0429229736328,
      "eval_loss": 0.00444964412599802,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -19.494667053222656,
      "eval_rewards/margins": 16.58540916442871,
      "eval_rewards/real": -2.9092600345611572,
      "eval_runtime": 204.6616,
      "eval_samples_per_second": 14.947,
      "eval_steps_per_second": 0.469,
      "step": 400
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.199079401611047e-07,
      "logits/generated": -2.6259143352508545,
      "logits/real": -2.300457715988159,
      "logps/generated": -290.53521728515625,
      "logps/real": -162.45645141601562,
      "loss": 0.0028,
      "rewards/accuracies": 1.0,
      "rewards/generated": -19.268831253051758,
      "rewards/margins": 16.62887954711914,
      "rewards/real": -2.639953136444092,
      "step": 410
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.141542002301496e-07,
      "logits/generated": -2.666271686553955,
      "logits/real": -2.375044822692871,
      "logps/generated": -279.67327880859375,
      "logps/real": -151.66567993164062,
      "loss": 0.0029,
      "rewards/accuracies": 1.0,
      "rewards/generated": -18.13127326965332,
      "rewards/margins": 16.91461944580078,
      "rewards/real": -1.2166534662246704,
      "step": 420
    },
    {
      "epoch": 0.45,
      "learning_rate": 3.084004602991945e-07,
      "logits/generated": -2.6066956520080566,
      "logits/real": -2.293417453765869,
      "logps/generated": -258.7156677246094,
      "logps/real": -147.15286254882812,
      "loss": 0.0014,
      "rewards/accuracies": 1.0,
      "rewards/generated": -16.97854995727539,
      "rewards/margins": 15.48681926727295,
      "rewards/real": -1.4917291402816772,
      "step": 430
    },
    {
      "epoch": 0.46,
      "learning_rate": 3.0264672036823936e-07,
      "logits/generated": -2.6187453269958496,
      "logits/real": -2.354405164718628,
      "logps/generated": -265.3907775878906,
      "logps/real": -138.26358032226562,
      "loss": 0.0042,
      "rewards/accuracies": 1.0,
      "rewards/generated": -17.276254653930664,
      "rewards/margins": 16.339208602905273,
      "rewards/real": -0.9370460510253906,
      "step": 440
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.968929804372842e-07,
      "logits/generated": -2.6384592056274414,
      "logits/real": -2.303077220916748,
      "logps/generated": -284.4481201171875,
      "logps/real": -131.69757080078125,
      "loss": 0.0028,
      "rewards/accuracies": 1.0,
      "rewards/generated": -18.245807647705078,
      "rewards/margins": 17.257396697998047,
      "rewards/real": -0.9884088635444641,
      "step": 450
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.911392405063291e-07,
      "logits/generated": -2.6308979988098145,
      "logits/real": -2.2776103019714355,
      "logps/generated": -267.861083984375,
      "logps/real": -134.22706604003906,
      "loss": 0.0029,
      "rewards/accuracies": 1.0,
      "rewards/generated": -17.91352081298828,
      "rewards/margins": 17.15715980529785,
      "rewards/real": -0.7563601136207581,
      "step": 460
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.85385500575374e-07,
      "logits/generated": -2.5978455543518066,
      "logits/real": -2.328986644744873,
      "logps/generated": -290.362548828125,
      "logps/real": -139.283447265625,
      "loss": 0.0016,
      "rewards/accuracies": 1.0,
      "rewards/generated": -19.644336700439453,
      "rewards/margins": 18.472408294677734,
      "rewards/real": -1.1719263792037964,
      "step": 470
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.7963176064441886e-07,
      "logits/generated": -2.6002590656280518,
      "logits/real": -2.30232310295105,
      "logps/generated": -288.4560546875,
      "logps/real": -130.22457885742188,
      "loss": 0.0004,
      "rewards/accuracies": 1.0,
      "rewards/generated": -19.87538719177246,
      "rewards/margins": 18.871204376220703,
      "rewards/real": -1.004183053970337,
      "step": 480
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.738780207134637e-07,
      "logits/generated": -2.5900683403015137,
      "logits/real": -2.307507038116455,
      "logps/generated": -293.84735107421875,
      "logps/real": -131.89328002929688,
      "loss": 0.0012,
      "rewards/accuracies": 1.0,
      "rewards/generated": -19.880746841430664,
      "rewards/margins": 18.607959747314453,
      "rewards/real": -1.272784948348999,
      "step": 490
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.681242807825086e-07,
      "logits/generated": -2.5825390815734863,
      "logits/real": -2.273686170578003,
      "logps/generated": -304.35394287109375,
      "logps/real": -143.6474609375,
      "loss": 0.001,
      "rewards/accuracies": 1.0,
      "rewards/generated": -20.637256622314453,
      "rewards/margins": 19.650598526000977,
      "rewards/real": -0.9866598844528198,
      "step": 500
    },
    {
      "epoch": 0.52,
      "eval_logits/generated": -2.571457624435425,
      "eval_logits/real": -2.275848388671875,
      "eval_logps/generated": -310.47198486328125,
      "eval_logps/real": -140.5501251220703,
      "eval_loss": 0.005000597331672907,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -21.721343994140625,
      "eval_rewards/margins": 20.16136360168457,
      "eval_rewards/real": -1.55997896194458,
      "eval_runtime": 203.6513,
      "eval_samples_per_second": 15.021,
      "eval_steps_per_second": 0.471,
      "step": 500
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.6237054085155355e-07,
      "logits/generated": -2.5877275466918945,
      "logits/real": -2.2942795753479004,
      "logps/generated": -306.7355651855469,
      "logps/real": -157.25070190429688,
      "loss": 0.0005,
      "rewards/accuracies": 1.0,
      "rewards/generated": -20.54067611694336,
      "rewards/margins": 19.110881805419922,
      "rewards/real": -1.4297946691513062,
      "step": 510
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.566168009205984e-07,
      "logits/generated": -2.566460132598877,
      "logits/real": -2.2550265789031982,
      "logps/generated": -302.12457275390625,
      "logps/real": -150.7072296142578,
      "loss": 0.0004,
      "rewards/accuracies": 1.0,
      "rewards/generated": -20.33761978149414,
      "rewards/margins": 18.86054801940918,
      "rewards/real": -1.4770714044570923,
      "step": 520
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.5086306098964327e-07,
      "logits/generated": -2.530325412750244,
      "logits/real": -2.147463321685791,
      "logps/generated": -325.1996765136719,
      "logps/real": -137.2005615234375,
      "loss": 0.0028,
      "rewards/accuracies": 1.0,
      "rewards/generated": -22.719600677490234,
      "rewards/margins": 21.01498794555664,
      "rewards/real": -1.7046133279800415,
      "step": 530
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.4510932105868813e-07,
      "logits/generated": -2.5007717609405518,
      "logits/real": -2.142106056213379,
      "logps/generated": -309.5279846191406,
      "logps/real": -145.54153442382812,
      "loss": 0.0013,
      "rewards/accuracies": 1.0,
      "rewards/generated": -21.59992027282715,
      "rewards/margins": 19.61166000366211,
      "rewards/real": -1.9882593154907227,
      "step": 540
    },
    {
      "epoch": 0.57,
      "learning_rate": 2.39355581127733e-07,
      "logits/generated": -2.5140461921691895,
      "logits/real": -2.1705541610717773,
      "logps/generated": -326.2548828125,
      "logps/real": -153.64620971679688,
      "loss": 0.0004,
      "rewards/accuracies": 1.0,
      "rewards/generated": -22.853506088256836,
      "rewards/margins": 21.288036346435547,
      "rewards/real": -1.5654710531234741,
      "step": 550
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.3360184119677789e-07,
      "logits/generated": -2.508565902709961,
      "logits/real": -2.086663246154785,
      "logps/generated": -324.4671325683594,
      "logps/real": -141.7945098876953,
      "loss": 0.0005,
      "rewards/accuracies": 1.0,
      "rewards/generated": -22.59902000427246,
      "rewards/margins": 20.527156829833984,
      "rewards/real": -2.0718634128570557,
      "step": 560
    },
    {
      "epoch": 0.59,
      "learning_rate": 2.2784810126582277e-07,
      "logits/generated": -2.5235228538513184,
      "logits/real": -2.136625051498413,
      "logps/generated": -317.3307800292969,
      "logps/real": -143.42645263671875,
      "loss": 0.0002,
      "rewards/accuracies": 1.0,
      "rewards/generated": -21.84872055053711,
      "rewards/margins": 19.594640731811523,
      "rewards/real": -2.2540805339813232,
      "step": 570
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.2209436133486764e-07,
      "logits/generated": -2.504979372024536,
      "logits/real": -2.160602569580078,
      "logps/generated": -326.36602783203125,
      "logps/real": -147.8289031982422,
      "loss": 0.0005,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.00318717956543,
      "rewards/margins": 21.120044708251953,
      "rewards/real": -1.883143424987793,
      "step": 580
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.1634062140391255e-07,
      "logits/generated": -2.501044511795044,
      "logits/real": -2.1728317737579346,
      "logps/generated": -342.8136901855469,
      "logps/real": -156.6595001220703,
      "loss": 0.0013,
      "rewards/accuracies": 1.0,
      "rewards/generated": -24.30771255493164,
      "rewards/margins": 22.852333068847656,
      "rewards/real": -1.4553799629211426,
      "step": 590
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.105868814729574e-07,
      "logits/generated": -2.469202756881714,
      "logits/real": -2.052633285522461,
      "logps/generated": -317.5489807128906,
      "logps/real": -143.7775421142578,
      "loss": 0.0004,
      "rewards/accuracies": 1.0,
      "rewards/generated": -22.429704666137695,
      "rewards/margins": 20.26901626586914,
      "rewards/real": -2.1606907844543457,
      "step": 600
    },
    {
      "epoch": 0.62,
      "eval_logits/generated": -2.4626379013061523,
      "eval_logits/real": -2.0544729232788086,
      "eval_logps/generated": -335.4198303222656,
      "eval_logps/real": -149.585205078125,
      "eval_loss": 0.002936215838417411,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -24.21613121032715,
      "eval_rewards/margins": 21.752639770507812,
      "eval_rewards/real": -2.463486909866333,
      "eval_runtime": 204.3596,
      "eval_samples_per_second": 14.969,
      "eval_steps_per_second": 0.47,
      "step": 600
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.048331415420023e-07,
      "logits/generated": -2.4702770709991455,
      "logits/real": -1.9979984760284424,
      "logps/generated": -344.7846984863281,
      "logps/real": -146.0871124267578,
      "loss": 0.0004,
      "rewards/accuracies": 1.0,
      "rewards/generated": -24.808910369873047,
      "rewards/margins": 22.57204246520996,
      "rewards/real": -2.2368671894073486,
      "step": 610
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.9907940161104716e-07,
      "logits/generated": -2.442737579345703,
      "logits/real": -1.9973560571670532,
      "logps/generated": -331.6400146484375,
      "logps/real": -155.714111328125,
      "loss": 0.0011,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.632118225097656,
      "rewards/margins": 20.816204071044922,
      "rewards/real": -2.8159143924713135,
      "step": 620
    },
    {
      "epoch": 0.65,
      "learning_rate": 1.9332566168009205e-07,
      "logits/generated": -2.4038469791412354,
      "logits/real": -2.053393602371216,
      "logps/generated": -335.13433837890625,
      "logps/real": -155.8861846923828,
      "loss": 0.0005,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.462812423706055,
      "rewards/margins": 20.91049575805664,
      "rewards/real": -2.552314281463623,
      "step": 630
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.8757192174913694e-07,
      "logits/generated": -2.4349865913391113,
      "logits/real": -1.9372657537460327,
      "logps/generated": -339.24432373046875,
      "logps/real": -161.06814575195312,
      "loss": 0.0011,
      "rewards/accuracies": 1.0,
      "rewards/generated": -24.555660247802734,
      "rewards/margins": 21.8681697845459,
      "rewards/real": -2.6874938011169434,
      "step": 640
    },
    {
      "epoch": 0.67,
      "learning_rate": 1.818181818181818e-07,
      "logits/generated": -2.4398064613342285,
      "logits/real": -2.024660348892212,
      "logps/generated": -350.3681945800781,
      "logps/real": -160.34848022460938,
      "loss": 0.0006,
      "rewards/accuracies": 1.0,
      "rewards/generated": -25.243322372436523,
      "rewards/margins": 22.082122802734375,
      "rewards/real": -3.1612000465393066,
      "step": 650
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.760644418872267e-07,
      "logits/generated": -2.4723610877990723,
      "logits/real": -2.2180397510528564,
      "logps/generated": -335.03302001953125,
      "logps/real": -153.06800842285156,
      "loss": 0.0005,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.727916717529297,
      "rewards/margins": 20.893634796142578,
      "rewards/real": -2.834282159805298,
      "step": 660
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.7031070195627155e-07,
      "logits/generated": -2.499124050140381,
      "logits/real": -2.1694862842559814,
      "logps/generated": -300.2198181152344,
      "logps/real": -158.0663604736328,
      "loss": 0.009,
      "rewards/accuracies": 1.0,
      "rewards/generated": -20.19024085998535,
      "rewards/margins": 18.492055892944336,
      "rewards/real": -1.6981853246688843,
      "step": 670
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.6455696202531644e-07,
      "logits/generated": -2.524540662765503,
      "logits/real": -2.1522810459136963,
      "logps/generated": -294.6327819824219,
      "logps/real": -153.84323120117188,
      "loss": 0.0006,
      "rewards/accuracies": 1.0,
      "rewards/generated": -19.780620574951172,
      "rewards/margins": 18.539196014404297,
      "rewards/real": -1.241428256034851,
      "step": 680
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.5880322209436133e-07,
      "logits/generated": -2.506713628768921,
      "logits/real": -2.0617382526397705,
      "logps/generated": -280.8321228027344,
      "logps/real": -132.4160614013672,
      "loss": 0.0004,
      "rewards/accuracies": 1.0,
      "rewards/generated": -18.93857765197754,
      "rewards/margins": 17.25060272216797,
      "rewards/real": -1.6879723072052002,
      "step": 690
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.5304948216340622e-07,
      "logits/generated": -2.5044121742248535,
      "logits/real": -2.153899669647217,
      "logps/generated": -295.0711975097656,
      "logps/real": -149.3346710205078,
      "loss": 0.0004,
      "rewards/accuracies": 1.0,
      "rewards/generated": -19.79727554321289,
      "rewards/margins": 17.852672576904297,
      "rewards/real": -1.9446029663085938,
      "step": 700
    },
    {
      "epoch": 0.72,
      "eval_logits/generated": -2.4823191165924072,
      "eval_logits/real": -2.0980000495910645,
      "eval_logps/generated": -300.6876525878906,
      "eval_logps/real": -144.76023864746094,
      "eval_loss": 0.0033771670423448086,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -20.742910385131836,
      "eval_rewards/margins": 18.761919021606445,
      "eval_rewards/real": -1.9809908866882324,
      "eval_runtime": 204.1886,
      "eval_samples_per_second": 14.981,
      "eval_steps_per_second": 0.47,
      "step": 700
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.4729574223245108e-07,
      "logits/generated": -2.479297637939453,
      "logits/real": -2.0620293617248535,
      "logps/generated": -310.3447570800781,
      "logps/real": -139.861328125,
      "loss": 0.0001,
      "rewards/accuracies": 1.0,
      "rewards/generated": -21.074228286743164,
      "rewards/margins": 19.46666145324707,
      "rewards/real": -1.6075658798217773,
      "step": 710
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.4154200230149597e-07,
      "logits/generated": -2.458987236022949,
      "logits/real": -1.9814422130584717,
      "logps/generated": -291.8255615234375,
      "logps/real": -135.95750427246094,
      "loss": 0.0049,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -20.021465301513672,
      "rewards/margins": 18.17797088623047,
      "rewards/real": -1.8434951305389404,
      "step": 720
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.3578826237054083e-07,
      "logits/generated": -2.432263135910034,
      "logits/real": -2.1026008129119873,
      "logps/generated": -293.8389892578125,
      "logps/real": -158.30062866210938,
      "loss": 0.0064,
      "rewards/accuracies": 0.987500011920929,
      "rewards/generated": -19.90408706665039,
      "rewards/margins": 16.62197494506836,
      "rewards/real": -3.282115936279297,
      "step": 730
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.3003452243958575e-07,
      "logits/generated": -2.437032699584961,
      "logits/real": -1.900973916053772,
      "logps/generated": -316.47039794921875,
      "logps/real": -163.98587036132812,
      "loss": 0.0013,
      "rewards/accuracies": 1.0,
      "rewards/generated": -21.978607177734375,
      "rewards/margins": 17.744993209838867,
      "rewards/real": -4.233611106872559,
      "step": 740
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.242807825086306e-07,
      "logits/generated": -2.396674633026123,
      "logits/real": -1.815617561340332,
      "logps/generated": -321.79071044921875,
      "logps/real": -167.52487182617188,
      "loss": 0.0007,
      "rewards/accuracies": 1.0,
      "rewards/generated": -22.713642120361328,
      "rewards/margins": 18.117107391357422,
      "rewards/real": -4.596534729003906,
      "step": 750
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.1852704257767548e-07,
      "logits/generated": -2.3993334770202637,
      "logits/real": -1.8101379871368408,
      "logps/generated": -330.94696044921875,
      "logps/real": -165.3904266357422,
      "loss": 0.0008,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.662656784057617,
      "rewards/margins": 19.446672439575195,
      "rewards/real": -4.215985298156738,
      "step": 760
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.1277330264672036e-07,
      "logits/generated": -2.421809196472168,
      "logits/real": -1.8476203680038452,
      "logps/generated": -327.7290954589844,
      "logps/real": -168.7994842529297,
      "loss": 0.0004,
      "rewards/accuracies": 1.0,
      "rewards/generated": -22.66012191772461,
      "rewards/margins": 18.314332962036133,
      "rewards/real": -4.345790863037109,
      "step": 770
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.0701956271576525e-07,
      "logits/generated": -2.3729705810546875,
      "logits/real": -1.9253933429718018,
      "logps/generated": -306.43426513671875,
      "logps/real": -166.4396209716797,
      "loss": 0.0021,
      "rewards/accuracies": 1.0,
      "rewards/generated": -21.686969757080078,
      "rewards/margins": 18.41327667236328,
      "rewards/real": -3.273693799972534,
      "step": 780
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.0126582278481012e-07,
      "logits/generated": -2.386841058731079,
      "logits/real": -1.9809033870697021,
      "logps/generated": -303.4554443359375,
      "logps/real": -177.92355346679688,
      "loss": 0.0022,
      "rewards/accuracies": 1.0,
      "rewards/generated": -21.421451568603516,
      "rewards/margins": 17.64752960205078,
      "rewards/real": -3.7739224433898926,
      "step": 790
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.551208285385501e-08,
      "logits/generated": -2.409217357635498,
      "logits/real": -1.844771146774292,
      "logps/generated": -312.0792541503906,
      "logps/real": -165.21864318847656,
      "loss": 0.0003,
      "rewards/accuracies": 1.0,
      "rewards/generated": -21.547452926635742,
      "rewards/margins": 17.484909057617188,
      "rewards/real": -4.062541961669922,
      "step": 800
    },
    {
      "epoch": 0.83,
      "eval_logits/generated": -2.3860702514648438,
      "eval_logits/real": -1.849648118019104,
      "eval_logps/generated": -329.3861389160156,
      "eval_logps/real": -167.8074493408203,
      "eval_loss": 0.0033722457010298967,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -23.612760543823242,
      "eval_rewards/margins": 19.327045440673828,
      "eval_rewards/real": -4.285713195800781,
      "eval_runtime": 203.8688,
      "eval_samples_per_second": 15.005,
      "eval_steps_per_second": 0.471,
      "step": 800
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.975834292289989e-08,
      "logits/generated": -2.418947696685791,
      "logits/real": -1.7803434133529663,
      "logps/generated": -331.84014892578125,
      "logps/real": -159.89285278320312,
      "loss": 0.0008,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.612918853759766,
      "rewards/margins": 19.30190086364746,
      "rewards/real": -4.311016082763672,
      "step": 810
    },
    {
      "epoch": 0.85,
      "learning_rate": 8.400460299194476e-08,
      "logits/generated": -2.385282516479492,
      "logits/real": -1.9237327575683594,
      "logps/generated": -326.67864990234375,
      "logps/real": -171.10238647460938,
      "loss": 0.0004,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.022621154785156,
      "rewards/margins": 18.915952682495117,
      "rewards/real": -4.106667518615723,
      "step": 820
    },
    {
      "epoch": 0.86,
      "learning_rate": 7.825086306098964e-08,
      "logits/generated": -2.400383472442627,
      "logits/real": -1.8308312892913818,
      "logps/generated": -330.8444519042969,
      "logps/real": -176.46241760253906,
      "loss": 0.0002,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.330158233642578,
      "rewards/margins": 19.13711166381836,
      "rewards/real": -4.193048000335693,
      "step": 830
    },
    {
      "epoch": 0.87,
      "learning_rate": 7.249712313003451e-08,
      "logits/generated": -2.40280818939209,
      "logits/real": -1.9568841457366943,
      "logps/generated": -330.2093200683594,
      "logps/real": -183.3866729736328,
      "loss": 0.0003,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.554615020751953,
      "rewards/margins": 19.334758758544922,
      "rewards/real": -4.2198567390441895,
      "step": 840
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.674338319907939e-08,
      "logits/generated": -2.3726344108581543,
      "logits/real": -1.8586174249649048,
      "logps/generated": -353.32037353515625,
      "logps/real": -168.06539916992188,
      "loss": 0.0003,
      "rewards/accuracies": 1.0,
      "rewards/generated": -25.464147567749023,
      "rewards/margins": 21.141162872314453,
      "rewards/real": -4.322987079620361,
      "step": 850
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.098964326812428e-08,
      "logits/generated": -2.383981227874756,
      "logits/real": -1.8769505023956299,
      "logps/generated": -347.90777587890625,
      "logps/real": -173.80300903320312,
      "loss": 0.0001,
      "rewards/accuracies": 1.0,
      "rewards/generated": -24.33977699279785,
      "rewards/margins": 20.448455810546875,
      "rewards/real": -3.891319990158081,
      "step": 860
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.523590333716915e-08,
      "logits/generated": -2.3623762130737305,
      "logits/real": -1.7878261804580688,
      "logps/generated": -336.87982177734375,
      "logps/real": -165.58560180664062,
      "loss": 0.0003,
      "rewards/accuracies": 1.0,
      "rewards/generated": -24.15330696105957,
      "rewards/margins": 20.214948654174805,
      "rewards/real": -3.938356876373291,
      "step": 870
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.9482163406214034e-08,
      "logits/generated": -2.3969762325286865,
      "logits/real": -1.8627573251724243,
      "logps/generated": -331.52215576171875,
      "logps/real": -160.87493896484375,
      "loss": 0.0005,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.688913345336914,
      "rewards/margins": 19.582998275756836,
      "rewards/real": -4.105912685394287,
      "step": 880
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.3728423475258916e-08,
      "logits/generated": -2.409092426300049,
      "logits/real": -1.825301170349121,
      "logps/generated": -333.3155517578125,
      "logps/real": -154.33688354492188,
      "loss": 0.0011,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.420581817626953,
      "rewards/margins": 19.293987274169922,
      "rewards/real": -4.126596450805664,
      "step": 890
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.79746835443038e-08,
      "logits/generated": -2.429063081741333,
      "logits/real": -1.9292951822280884,
      "logps/generated": -326.38360595703125,
      "logps/real": -161.9578399658203,
      "loss": 0.0003,
      "rewards/accuracies": 1.0,
      "rewards/generated": -22.63199806213379,
      "rewards/margins": 19.206939697265625,
      "rewards/real": -3.4250571727752686,
      "step": 900
    },
    {
      "epoch": 0.93,
      "eval_logits/generated": -2.389368772506714,
      "eval_logits/real": -1.8916875123977661,
      "eval_logps/generated": -336.8122863769531,
      "eval_logps/real": -163.09927368164062,
      "eval_loss": 0.002673720009624958,
      "eval_rewards/accuracies": 1.0,
      "eval_rewards/generated": -24.355375289916992,
      "eval_rewards/margins": 20.540477752685547,
      "eval_rewards/real": -3.814894437789917,
      "eval_runtime": 204.4163,
      "eval_samples_per_second": 14.965,
      "eval_steps_per_second": 0.47,
      "step": 900
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.222094361334868e-08,
      "logits/generated": -2.387352466583252,
      "logits/real": -1.8404461145401,
      "logps/generated": -353.838623046875,
      "logps/real": -161.55064392089844,
      "loss": 0.0001,
      "rewards/accuracies": 1.0,
      "rewards/generated": -25.344829559326172,
      "rewards/margins": 21.402610778808594,
      "rewards/real": -3.9422194957733154,
      "step": 910
    },
    {
      "epoch": 0.95,
      "learning_rate": 2.6467203682393555e-08,
      "logits/generated": -2.400730609893799,
      "logits/real": -1.9661195278167725,
      "logps/generated": -326.0292663574219,
      "logps/real": -175.82342529296875,
      "loss": 0.0003,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.205665588378906,
      "rewards/margins": 19.59792137145996,
      "rewards/real": -3.607743740081787,
      "step": 920
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.0713463751438434e-08,
      "logits/generated": -2.4410576820373535,
      "logits/real": -2.0028738975524902,
      "logps/generated": -325.7819519042969,
      "logps/real": -159.87515258789062,
      "loss": 0.0005,
      "rewards/accuracies": 1.0,
      "rewards/generated": -22.805809020996094,
      "rewards/margins": 19.58681869506836,
      "rewards/real": -3.2189908027648926,
      "step": 930
    },
    {
      "epoch": 0.97,
      "learning_rate": 1.4959723820483312e-08,
      "logits/generated": -2.371100425720215,
      "logits/real": -2.0735080242156982,
      "logps/generated": -329.3601989746094,
      "logps/real": -170.0877227783203,
      "loss": 0.0018,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.724470138549805,
      "rewards/margins": 20.690706253051758,
      "rewards/real": -3.033766746520996,
      "step": 940
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.205983889528193e-09,
      "logits/generated": -2.3900890350341797,
      "logits/real": -1.9221683740615845,
      "logps/generated": -323.7618408203125,
      "logps/real": -159.85540771484375,
      "loss": 0.0003,
      "rewards/accuracies": 1.0,
      "rewards/generated": -23.1872501373291,
      "rewards/margins": 19.602642059326172,
      "rewards/real": -3.584606647491455,
      "step": 950
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.452243958573072e-09,
      "logits/generated": -2.3842434883117676,
      "logits/real": -1.9066474437713623,
      "logps/generated": -340.50018310546875,
      "logps/real": -169.8536376953125,
      "loss": 0.0009,
      "rewards/accuracies": 1.0,
      "rewards/generated": -24.914575576782227,
      "rewards/margins": 20.938364028930664,
      "rewards/real": -3.9762122631073,
      "step": 960
    },
    {
      "epoch": 1.0,
      "step": 966,
      "total_flos": 0.0,
      "train_loss": 0.014407816406519693,
      "train_runtime": 6867.7564,
      "train_samples_per_second": 4.499,
      "train_steps_per_second": 0.141
    }
  ],
  "logging_steps": 10,
  "max_steps": 966,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}